mihirp1998 / AlignProp
AlignProp uses direct reward backpropogation for the alignment of large-scale text-to-image diffusion models. Our method is 25x more sample and compute efficient than reinforcement learning methods (PPO) for finetuning Stable Diffusion
☆279Updated 5 months ago
Alternatives and similar repositories for AlignProp:
Users that are interested in AlignProp are comparing it to the libraries listed below
- [CVPR 2024] Code for the paper "Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model"☆211Updated 11 months ago
- Code for "Diffusion Model Alignment Using Direct Preference Optimization"☆408Updated last month
- Smooth Diffusion: Crafting Smooth Latent Spaces in Diffusion Models arXiv 2023 / CVPR 2024☆336Updated 6 months ago
- GenEval: An object-focused framework for evaluating text-to-image alignment☆208Updated 3 weeks ago
- [Neurips 2023 & TPAMI] T2I-CompBench (++) for Compositional Text-to-image Generation Evaluation☆245Updated last week
- [NeurIPS 2024] ReNO: Enhancing One-step Text-to-Image Models through Reward-based Noise Optimization☆131Updated 2 months ago
- [ICCV 2023] Efficient Diffusion Training via Min-SNR Weighting Strategy☆243Updated 3 months ago
- (CVPR 2024) 🧩 TokenCompose: Text-to-Image Diffusion with Token-level Supervision☆120Updated 3 months ago
- [WACV 2024] Training-Free Layout Control with Cross-Attention Guidance☆253Updated last year
- [CVPR 2025] Aesthetic Post-Training Diffusion Models from Generic Preferences with Step-by-step Preference Optimization☆192Updated last week
- Better Aligning Text-to-Image Models with Human Preference. ICCV 2023☆278Updated last year
- A one-stop library to standardize the inference and evaluation of all the conditional image generation models. (ICLR 2024)☆167Updated last week
- Video Diffusion Alignment via Reward Gradients. We improve a variety of video diffusion models such as VideoCrafter, OpenSora, ModelScope…☆255Updated 3 weeks ago
- Official implementation of "Controlling Text-to-Image Diffusion by Orthogonal Finetuning".☆289Updated 5 months ago
- MoVQGAN - model for the image encoding and reconstruction☆226Updated last year
- 🔥 [CVPR2024] Official implementation of "Self-correcting LLM-controlled Diffusion Models (SLD)☆170Updated 11 months ago
- Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis☆470Updated 10 months ago
- ☆493Updated 3 months ago
- VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation☆198Updated last week
- [CVPR 2024] | LAMP: Learn a Motion Pattern for Few-Shot Based Video Generation☆278Updated 11 months ago
- [ECCV 2024] Official PyTorch implementation of "Getting it Right: Improving Spatial Consistency in Text-to-Image Models"☆100Updated 8 months ago
- Official PyTorch implementation of the paper "In-Context Learning Unlocked for Diffusion Models"☆399Updated last year
- 🚀 Cross attention map tools for huggingface/diffusers☆243Updated 2 months ago
- Official pytorch implementation of the paper: "An Edit Friendly DDPM Noise Space: Inversion and Manipulations". CVPR 2024.☆326Updated 8 months ago
- ☆121Updated 8 months ago
- Implementation of "DiffFit: Unlocking Transferability of Large Diffusion Models via Simple Parameter-Efficient Fine-Tuning"☆85Updated last year
- [ICLR 2025] Rectified Diffusion: Straightness Is Not Your Need☆203Updated 3 weeks ago
- An in-context conditioning version of MUSE with pre-trained checkpoints.☆111Updated last year
- Official PyTorch implementation for ICLR2024 paper "The Blessing of Randomness: SDE Beats ODE in General Diffusion-based Image Editing"☆110Updated last year
- [ICML 2024 Spotlight] FiT: Flexible Vision Transformer for Diffusion Model☆408Updated 4 months ago